Song Han

Computer Science · Physical Sciences

58h-index33.5kcitations228works2.72yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(89), Domain Adaptation and Few-Shot Learning(25), Adversarial Robustness in Machine Learning(24), Quantum Computing Algorithms and Architecture(22), Quantum Information and Cryptography(18)

Publications228 total

Data Science and Technology Towards AGI Part I: Tiered Data Management
arXiv (Cornell University)·2026Open Access
Data Science and Technology Towards AGI Part I: Tiered Data Management
arXiv (Cornell University)·2026Open Access
SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization
ArXiv.org·2026Open Access
SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization
arXiv (Cornell University)·2026Open Access
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
arXiv (Cornell University)·2025Open Access
Sailor: Automating Distributed Training over Dynamic, Heterogeneous, and Geo-distributed Clusters
2025Open Access
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
arXiv (Cornell University)·2025Open Access
Deep Neural Architecture Combining Frequency and Attention Mechanisms for Cloud CPU Usage Prediction
2025Open Access
Deep Neural Architecture Combining Frequency and Attention Mechanisms for Cloud CPU Usage Prediction
2025· 7 cited
Micromobility Flow Prediction: A Bike Sharing Station-level Study via Multi-level Spatial-Temporal Attention Neural Network
arXiv (Cornell University)·2025Open Access
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
ArXiv.org·2025Open Access
Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
arXiv (Cornell University)·2025Open Access
QPlacer: Frequency-Aware Component Placement for Superconducting Quantum Computers
2025
Transitive Array: An Efficient GEMM Accelerator with Result Reuse
2025· 2 citedOpen Access
Transitive Array: An Efficient GEMM Accelerator with Result Reuse
arXiv (Cornell University)·2025Open Access
Sailor: Automating Distributed Training over Dynamic, Heterogeneous, and Geo-distributed Clusters
arXiv (Cornell University)·2025Open Access
LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications
2025Open Access
LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
arXiv (Cornell University)·2025· 1 citedOpen Access
Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning
arXiv (Cornell University)·2025Open Access
GR-WiFi: A GNU Radio based WiFi Platform with Single-User and Multi-User MIMO Capability
arXiv (Cornell University)·2025Open Access
page 1 of 12Next →

Frequent Co-authors

William J. Dally(14), Ji Lin(14), Yujun Lin(12), Zhijian Liu(11), Huizi Mao(10), Hanrui Wang(10), Han Cai(9), Chuang Gan(8), Ligeng Zhu(6), Xingyu Liu(4), Haotian Tang(4), Zhekai Zhang(4), Jeff Pool(4), Kuan Wang(3), Yu Wang(3), Huazhong Yang(3), Wei-Ming Chen(3), Jing Pu(2), Ardavan Pedram(2), Mark Horowitz(2)